Mathematical Reasoning on AIME 2025 (Acc, Len, Red.)
39.2AccuracyOPSDC
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OPSDCBase Model=Qwen3-14B, Token Budget=8,192 tokens2026.03 | 39.2 | 5,484 | 26.6 | |
| OPSDCBase Model=Qwen3-8B, Token Budget=8,192 tokens2026.03 | 36.3 | 5,658 | 26.2 | |
| Concise promptBase Model=Qwen3-14B, Token Budget=8,192 tokens2026.03 | 30.8 | 6,852 | 8.3 | |
| Concise promptBase Model=Qwen3-8B, Token Budget=8,192 tokens2026.03 | 29.2 | 7,140 | 6.8 | |
| Base ModelBase Model=Qwen3-14B, Token Budget=8,192 tokens2026.03 | 19.6 | 7,471 | — | |
| Base ModelBase Model=Qwen3-8B, Token Budget=8,192 tokens2026.03 | 18.8 | 7,661 | — |